Title :
Forward smoothing and online expectation-maximisation in Gaussian linear state-space models
Author :
Sinan Yıldırım;A. Taylan Cemgil
Author_Institution :
Statistical Laboratory, Cambridge Ü
fDate :
4/1/2011 12:00:00 AM
Abstract :
In this work, we studied forward-only smoothing recursion in Gaussian linear state-space (GLSS) models. We exploited a stochastic approximation of this recursion to develop an online version of the expectation-maximisation (EM) algorithm for GLSS models. We compared the performance of online EM with the conventional EM and demonstrated the advantages of its use in case of long data sequences.
Keywords :
"Markov processes","Hidden Markov models","Signal processing","Conferences","Signal processing algorithms","Smoothing methods","Art"
Conference_Titel :
Signal Processing and Communications Applications (SIU), 2011 IEEE 19th Conference on
Print_ISBN :
978-1-4577-0462-8
DOI :
10.1109/SIU.2011.5929704
